← authors · overview

• Conformer: Convolution-augmented Transformer for Speech Recognition
  2020 · 2748 citations
• Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis
  2018 · 475 citations
• Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis
  2018 · 435 citations
• W2v-BERT: Combining Contrastive Learning and Masked Language Modeling for Self-Supervised Speech Pre-Training
  2021 · 262 citations
• ContextNet: Improving Convolutional Neural Networks for Automatic Speech Recognition with Global Context
  2020 · 257 citations
• A Streaming On-Device End-to-End Model Surpassing Server-Side Conventional Model Quality and Latency
  2020 · 202 citations
• Fully-hierarchical fine-grained prosody modeling for interpretable speech synthesis
  2020 · 93 citations
• SpeechStew: Simply Mix All Available Speech Recognition Data to Train One Large Neural Network
  2021 · 75 citations
• Non-Attentive Tacotron: Robust and Controllable Neural TTS Synthesis Including Unsupervised Duration Modeling